INDEX

Explanations

numeric values and version indicators associated with software

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

corn

-0.18

eature

-0.15

rent

-0.15

 ÑĩÐ¸Ð½

-0.14

å¹¹ç·ļ

-0.14

orsk

-0.14

hang

-0.14

etail

-0.14

endas

-0.14

ansen

-0.14

POSITIVE LOGITS

 inse

0.17

_iff

0.17

 hedge

0.16

Ä©

0.15

apl

0.15

 casting

0.15

pi

0.15

Kn

0.14

fov

0.14

pi

0.14

Activations Density 0.044%

numeric values and version indicators associated with software

No Comments

No Known Activations